def classifier_multiclassmachine_modular(fm_train_real=traindat,
fm_test_real=testdat,
label_train_multiclass=label_traindat,
width=2.1,
C=1,
epsilon=1e-5):
from shogun.Features import RealFeatures, MulticlassLabels
from shogun.Kernel import GaussianKernel
from shogun.Classifier import LibSVM, KernelMulticlassMachine, MulticlassOneVsRestStrategy
feats_train = RealFeatures(fm_train_real)
feats_test = RealFeatures(fm_test_real)
kernel = GaussianKernel(feats_train, feats_train, width)
labels = MulticlassLabels(label_train_multiclass)
classifier = LibSVM()
classifier.set_epsilon(epsilon)
print labels.get_labels()
mc_classifier = KernelMulticlassMachine(MulticlassOneVsRestStrategy(),
kernel, classifier, labels)
mc_classifier.train()
kernel.init(feats_train, feats_test)
out = mc_classifier.apply().get_labels()
return out
class svm_splice_model(object):
def __init__(self, order, traindat, alphas, b, (window_left, offset,
window_right), consensus):
f = StringCharFeatures(traindat, DNA)
wd_kernel = WeightedDegreeStringKernel(f, f, int(order))
wd_kernel.io.set_target_to_stdout()
self.svm = LibSVM()
self.svm.set_kernel(wd_kernel)
self.svm.set_alphas(alphas)
self.svm.set_support_vectors(
numpy.arange(len(alphas), dtype=numpy.int32))
self.svm.set_bias(b)
self.svm.io.set_target_to_stdout()
self.svm.parallel.set_num_threads(self.svm.parallel.get_num_cpus())
self.svm.set_linadd_enabled(True)
self.svm.set_batch_computation_enabled(True)
self.window_left = int(window_left)
self.window_right = int(window_right)
self.consensus = consensus
self.wd_kernel = wd_kernel
self.traindat = f
self.offset = offset
def classifier_libsvm_modular(fm_train_real=traindat,
fm_test_real=testdat,
label_train_twoclass=label_traindat,
width=2.1,
C=1,
epsilon=1e-5):
from shogun.Features import RealFeatures, Labels
from shogun.Kernel import GaussianKernel
from shogun.Classifier import LibSVM
feats_train = RealFeatures(fm_train_real)
feats_test = RealFeatures(fm_test_real)
kernel = GaussianKernel(feats_train, feats_train, width)
labels = Labels(label_train_twoclass)
svm = LibSVM(C, kernel, labels)
svm.set_epsilon(epsilon)
svm.train()
kernel.init(feats_train, feats_test)
labels = svm.classify().get_labels()
supportvectors = sv_idx = svm.get_support_vectors()
alphas = svm.get_alphas()
predictions = svm.classify()
return predictions, svm, predictions.get_labels()
def svm_learn(kernel, labels, options):
"""train SVM using SVMLight or LibSVM
Arguments:
kernel -- kernel object from Shogun toolbox
lebels -- list of labels
options -- object containing option data
Return:
trained svm object
"""
try:
svm = SVMLight(options.svmC, kernel,
Labels(numpy.array(labels, dtype=numpy.double)))
except NameError:
svm = LibSVM(options.svmC, kernel,
Labels(numpy.array(labels, dtype=numpy.double)))
if options.quiet == False:
svm.io.set_loglevel(MSG_INFO)
svm.io.set_target_to_stderr()
svm.set_epsilon(options.epsilon)
svm.parallel.set_num_threads(1)
if options.weight != 1.0:
svm.set_C(options.svmC, options.svmC * options.weight)
svm.train()
if options.quiet == False:
svm.io.set_loglevel(MSG_ERROR)
return svm
def libsvm():
print 'LibSVM'
from shogun.Features import RealFeatures, Labels
from shogun.Kernel import GaussianKernel
from shogun.Evaluation import PerformanceMeasures
from shogun.Classifier import LibSVM
feats_train = RealFeatures(fm_train_real)
feats_test = RealFeatures(fm_test_real)
width = 2.1
kernel = GaussianKernel(feats_train, feats_train, width)
C = 1
epsilon = 1e-5
labels = Labels(label_train_twoclass)
svm = LibSVM(C, kernel, labels)
svm.set_epsilon(epsilon)
svm.train()
#kernel.init(feats_train, feats_test)
output = svm.classify(feats_test) #.get_labels()
#output_vector = output.get_labels()
out = svm.classify().get_labels()
testerr = mean(sign(out) != testlab)
print testerr
def modelselection_grid_search_kernel():
num_subsets = 3
num_vectors = 20
dim_vectors = 3
# create some (non-sense) data
matrix = rand(dim_vectors, num_vectors)
# create num_feautres 2-dimensional vectors
features = RealFeatures()
features.set_feature_matrix(matrix)
# create labels, two classes
labels = Labels(num_vectors)
for i in range(num_vectors):
labels.set_label(i, 1 if i % 2 == 0 else -1)
# create svm
classifier = LibSVM()
# splitting strategy
splitting_strategy = StratifiedCrossValidationSplitting(
labels, num_subsets)
# accuracy evaluation
evaluation_criterion = ContingencyTableEvaluation(ACCURACY)
# cross validation class for evaluation in model selection
cross = CrossValidation(classifier, features, labels, splitting_strategy,
evaluation_criterion)
cross.set_num_runs(1)
# print all parameter available for modelselection
# Dont worry if yours is not included, simply write to the mailing list
classifier.print_modsel_params()
# model parameter selection
param_tree = create_param_tree()
param_tree.print_tree()
grid_search = GridSearchModelSelection(param_tree, cross)
print_state = True
best_combination = grid_search.select_model(print_state)
print("best parameter(s):")
best_combination.print_tree()
best_combination.apply_to_machine(classifier)
# larger number of runs to have tighter confidence intervals
cross.set_num_runs(10)
cross.set_conf_int_alpha(0.01)
result = cross.evaluate()
print("result: ")
result.print_result()
return 0
def modelselection_grid_search_kernel (num_subsets, num_vectors, dim_vectors):
# init seed for reproducability
Math.init_random(1)
random.seed(1);
# create some (non-sense) data
matrix=random.rand(dim_vectors, num_vectors)
# create num_feautres 2-dimensional vectors
features=RealFeatures()
features.set_feature_matrix(matrix)
# create labels, two classes
labels=BinaryLabels(num_vectors)
for i in range(num_vectors):
labels.set_label(i, 1 if i%2==0 else -1)
# create svm
classifier=LibSVM()
# splitting strategy
splitting_strategy=StratifiedCrossValidationSplitting(labels, num_subsets)
# accuracy evaluation
evaluation_criterion=ContingencyTableEvaluation(ACCURACY)
# cross validation class for evaluation in model selection
cross=CrossValidation(classifier, features, labels, splitting_strategy, evaluation_criterion)
cross.set_num_runs(1)
# print all parameter available for modelselection
# Dont worry if yours is not included, simply write to the mailing list
#classifier.print_modsel_params()
# model parameter selection
param_tree=create_param_tree()
#param_tree.print_tree()
grid_search=GridSearchModelSelection(param_tree, cross)
print_state=False
best_combination=grid_search.select_model(print_state)
#print("best parameter(s):")
#best_combination.print_tree()
best_combination.apply_to_machine(classifier)
# larger number of runs to have tighter confidence intervals
cross.set_num_runs(10)
cross.set_conf_int_alpha(0.01)
result=cross.evaluate()
casted=CrossValidationResult.obtain_from_generic(result);
#print "result mean:", casted.mean
return classifier,result,casted.mean
def evaluation_cross_validation_mkl_weight_storage(traindat=traindat, label_traindat=label_traindat):
from shogun.Evaluation import CrossValidation, CrossValidationResult
from shogun.Evaluation import CrossValidationPrintOutput
from shogun.Evaluation import CrossValidationMKLStorage
from shogun.Evaluation import ContingencyTableEvaluation, ACCURACY
from shogun.Evaluation import StratifiedCrossValidationSplitting
from shogun.Features import BinaryLabels
from shogun.Features import RealFeatures, CombinedFeatures
from shogun.Kernel import GaussianKernel, CombinedKernel
from shogun.Classifier import LibSVM, MKLClassification
from shogun.Mathematics import Statistics
# training data, combined features all on same data
features=RealFeatures(traindat)
comb_features=CombinedFeatures()
comb_features.append_feature_obj(features)
comb_features.append_feature_obj(features)
comb_features.append_feature_obj(features)
labels=BinaryLabels(label_traindat)
# kernel, different Gaussians combined
kernel=CombinedKernel()
kernel.append_kernel(GaussianKernel(10, 0.1))
kernel.append_kernel(GaussianKernel(10, 1))
kernel.append_kernel(GaussianKernel(10, 2))
# create mkl using libsvm, due to a mem-bug, interleaved is not possible
svm=MKLClassification(LibSVM());
svm.set_interleaved_optimization_enabled(False);
svm.set_kernel(kernel);
# splitting strategy for 5 fold cross-validation (for classification its better
# to use "StratifiedCrossValidation", but the standard
# "StratifiedCrossValidationSplitting" is also available
splitting_strategy=StratifiedCrossValidationSplitting(labels, 5)
# evaluation method
evaluation_criterium=ContingencyTableEvaluation(ACCURACY)
# cross-validation instance
cross_validation=CrossValidation(svm, comb_features, labels,
splitting_strategy, evaluation_criterium)
cross_validation.set_autolock(False)
# append cross vlaidation output classes
#cross_validation.add_cross_validation_output(CrossValidationPrintOutput())
mkl_storage=CrossValidationMKLStorage()
cross_validation.add_cross_validation_output(mkl_storage)
cross_validation.set_num_runs(3)
# perform cross-validation
result=cross_validation.evaluate()
# print mkl weights
weights=mkl_storage.get_mkl_weights()
def svm_train(kernel, labels, C1, C2=None):
"""Trains a SVM with the given kernel"""
num_threads = 1
kernel.io.disable_progress()
svm = LibSVM(C1, kernel, labels)
if C2:
svm.set_C(C1, C2)
svm.parallel.set_num_threads(num_threads)
svm.io.disable_progress()
svm.train()
return svm
def init_svm(task_type, kernel, labels):
"""A factory for creating the right svm type"""
C=1
epsilon=1e-5
if task_type == 'Binary Classification':
svm = LibSVM(C, kernel, labels)
elif task_type == 'Multi Class Classification':
svm = LibSVMMultiClass(C, kernel, labels)
elif task_type == 'Regression':
tube_epsilon=1e-2
svm=LibSVR(C, epsilon, kernel, labels)
svm.set_tube_epsilon(tube_epsilon)
else:
print(task_type + ' unknown!')
return svm
def kernel_combined_custom_poly_modular(fm_train_real=traindat,
fm_test_real=testdat,
fm_label_twoclass=label_traindat):
from shogun.Features import CombinedFeatures, RealFeatures, Labels
from shogun.Kernel import CombinedKernel, PolyKernel, CustomKernel
from shogun.Classifier import LibSVM
kernel = CombinedKernel()
feats_train = CombinedFeatures()
tfeats = RealFeatures(fm_train_real)
tkernel = PolyKernel(10, 3)
tkernel.init(tfeats, tfeats)
K = tkernel.get_kernel_matrix()
kernel.append_kernel(CustomKernel(K))
subkfeats_train = RealFeatures(fm_train_real)
feats_train.append_feature_obj(subkfeats_train)
subkernel = PolyKernel(10, 2)
kernel.append_kernel(subkernel)
kernel.init(feats_train, feats_train)
labels = Labels(fm_label_twoclass)
svm = LibSVM(1.0, kernel, labels)
svm.train()
kernel = CombinedKernel()
feats_pred = CombinedFeatures()
pfeats = RealFeatures(fm_test_real)
tkernel = PolyKernel(10, 3)
tkernel.init(tfeats, pfeats)
K = tkernel.get_kernel_matrix()
kernel.append_kernel(CustomKernel(K))
subkfeats_test = RealFeatures(fm_test_real)
feats_pred.append_feature_obj(subkfeats_test)
subkernel = PolyKernel(10, 2)
kernel.append_kernel(subkernel)
kernel.init(feats_train, feats_pred)
svm.set_kernel(kernel)
svm.classify()
km_train = kernel.get_kernel_matrix()
return km_train, kernel
def bench_shogun(X, y, T, valid):
#
# .. Shogun ..
#
from shogun.Classifier import LibSVM
from shogun.Features import RealFeatures, Labels
from shogun.Kernel import GaussianKernel
start = datetime.now()
feat = RealFeatures(X.T)
feat_test = RealFeatures(T.T)
labels = Labels(y.astype(np.float64))
kernel = GaussianKernel(feat, feat, sigma)
shogun_svm = LibSVM(1., kernel, labels)
shogun_svm.train()
dec_func = shogun_svm.classify(feat_test).get_labels()
score = np.mean(np.sign(dec_func) == valid)
return score, datetime.now() - start
def classifier_libsvm_minimal_modular(fm_train_real=traindat,
fm_test_real=testdat,
label_train_twoclass=label_traindat,
width=2.1,
C=1):
from shogun.Features import RealFeatures, BinaryLabels
from shogun.Classifier import LibSVM
from shogun.Kernel import GaussianKernel
feats_train = RealFeatures(fm_train_real)
feats_test = RealFeatures(fm_test_real)
kernel = GaussianKernel(feats_train, feats_train, width)
labels = BinaryLabels(label_train_twoclass)
svm = LibSVM(C, kernel, labels)
svm.train()
kernel.init(feats_train, feats_test)
out = svm.apply().get_labels()
testerr = mean(sign(out) != label_train_twoclass)
def classifier_custom_kernel_modular(C=1, dim=7):
from shogun.Features import RealFeatures, Labels
from shogun.Kernel import CustomKernel
from shogun.Classifier import LibSVM
from numpy import diag, ones, sign
from numpy.random import rand, seed
seed((C, dim))
lab = sign(2 * rand(dim) - 1)
data = rand(dim, dim)
symdata = data * data.T + diag(ones(dim))
kernel = CustomKernel()
kernel.set_full_kernel_matrix_from_full(data)
labels = Labels(lab)
svm = LibSVM(C, kernel, labels)
svm.train()
predictions = svm.apply()
out = svm.apply().get_labels()
return svm, out
labels_presvm[2] = 1 labels_presvm[12] = 1 labels_presvm[15] = 1 labels_presvm[8] = 1 labels_presvm[19] = 1 feat_presvm = StringCharFeatures(DNA) feat_presvm.set_features(examples_presvm) wdk_presvm = WeightedDegreeStringKernel(feat_presvm, feat_presvm, 1) lab_presvm = Labels(numpy.array(labels_presvm)) presvm = SVMLight(1, wdk_presvm, lab_presvm) presvm.train() presvm2 = LibSVM(1, wdk_presvm, lab_presvm) presvm2.train() print "svmlight", presvm.get_objective() print "libsvm", presvm2.get_objective() assert (abs(presvm.get_objective() - presvm2.get_objective()) <= 0.001) print "simple svm", presvm.get_objective() print "len(examples_presvm)", len(examples_presvm) print "##############" ############################################# # compute linear term manually
from numpy import random
from shogun.Classifier import LibSVM
from shogun.Features import RealFeatures, Labels
from shogun.Kernel import LinearKernel
num_feats = 23
num_vec = 42
scale = 2.1
size_cache = 10
C = 0.017
epsilon = 1e-5
tube_epsilon = 1e-2
svm = LibSVM()
svm.set_C(C, C)
svm.set_epsilon(epsilon)
svm.set_tube_epsilon(tube_epsilon)
for i in xrange(3):
data_train = random.rand(num_feats, num_vec)
data_test = random.rand(num_feats, num_vec)
feats_train = RealFeatures(data_train)
feats_test = RealFeatures(data_test)
labels = Labels(random.rand(num_vec).round() * 2 - 1)
svm.set_kernel(LinearKernel(size_cache, scale))
svm.set_labels(labels)
kernel = svm.get_kernel()
##################################################################
km = wdk.get_kernel_matrix()
for i in xrange(N):
for j in xrange(N):
km[i, j] = km[i, j] * relate_tasks(i, j)
#km = km*1.0
print km
#precompute kernel matrix using shogun
y = numpy.array(labels)
K = numpy.transpose(y.flatten() * (km * y.flatten()).transpose())
f = -numpy.ones(N)
C = 1.0
# Important!! QP does not accept ndarray as a type, it must be an array
p = QP(K, f, Aeq=y, beq=0, lb=numpy.zeros(N), ub=C * numpy.ones(N))
r = p.solve('cvxopt_qp', iprint=0)
#print "cvxopt objective:", r.ff
print "externally modified kernel. objective:", r.ff
ck = CustomKernel()
ck.set_full_kernel_matrix_from_full(km)
#
svm = LibSVM(1, ck, lab)
svm.train()
print "externally modified kernel. objective:", svm.get_objective()
############################################# # create real-valued features as first step examples_presvm = numpy.array(examples_presvm, dtype=numpy.float64) examples_presvm = numpy.transpose(examples_presvm) feat_presvm = RealFeatures(examples_presvm) lab_presvm = Labels(numpy.array(labels_presvm)) wdk_presvm = LinearKernel(feat_presvm, feat_presvm) presvm_liblinear = LibLinear(1, feat_presvm, lab_presvm) presvm_liblinear.set_max_iterations(10000) presvm_liblinear.set_bias_enabled(False) presvm_liblinear.train() presvm_libsvm = LibSVM(1, wdk_presvm, lab_presvm) #presvm_libsvm = SVMLight(1, wdk_presvm, lab_presvm) #presvm_libsvm.io.set_loglevel(MSG_DEBUG) presvm_libsvm.set_bias_enabled(False) presvm_libsvm.train() my_w = presvm_liblinear.get_w() presvm_liblinear = LibLinear(1, feat_presvm, lab_presvm) presvm_liblinear.set_w(my_w) ############################################# # compute linear term manually ############################################# examples = numpy.array(examples, dtype=numpy.float64)
from shogun.Classifier import LibSVM, LDA
from shogun.Evaluation import PRCEvaluation
import util
util.set_title('PRC example')
util.DISTANCE=0.5
subplots_adjust(hspace=0.3)
pos=util.get_realdata(True)
neg=util.get_realdata(False)
features=util.get_realfeatures(pos, neg)
labels=util.get_labels()
# classifiers
gk=GaussianKernel(features, features, 1.0)
svm = LibSVM(1000.0, gk, labels)
svm.train()
lda=LDA(1,features,labels)
lda.train()
## plot points
subplot(211)
plot(pos[0,:], pos[1,:], "r.")
plot(neg[0,:], neg[1,:], "b.")
grid(True)
title('Data',size=10)
# plot PRC for SVM
subplot(223)
PRC_evaluation=PRCEvaluation()
PRC_evaluation.evaluate(svm.classify(),labels)
def training_run(options):
"""Conduct a training run and return a trained SVM kernel"""
settings = MotifFinderSettings(kirmes_ini.MOTIF_LENGTH,
options.window_width, options.replace)
positives = MotifFinder(finder_settings=settings)
positives.setFastaFile(options.positives)
positives.setMotifs(options.pgff)
pmotifs, ppositions = positives.getResults()
negatives = MotifFinder(finder_settings=settings)
negatives.setFastaFile(options.negatives)
negatives.setMotifs(options.ngff)
nmotifs, npositions = negatives.getResults()
wds_kparams = kirmes_ini.WDS_KERNEL_PARAMETERS
wds_svm = EasySVM.EasySVM(wds_kparams)
num_positives = len(pmotifs.values()[0])
num_negatives = len(nmotifs.values()[0])
#Creating Kernel Objects
kernel = CombinedKernel()
features = CombinedFeatures()
kernel_array = []
motifs = pmotifs.keys()
motifs.sort()
#Adding Kmer Kernels
for motif in motifs:
all_examples = pmotifs[motif] + nmotifs[motif]
motif_features = wds_svm.createFeatures(all_examples)
wds_kernel = WeightedDegreePositionStringKernel(motif_features, motif_features, \
wds_kparams['degree'])
wds_kernel.set_shifts(wds_kparams['shift'] *
ones(wds_kparams['seqlength'], dtype=int32))
features.append_feature_obj(motif_features)
kernel_array.append(wds_kernel)
kernel.append_kernel(wds_kernel)
rbf_svm = EasySVM.EasySVM(kirmes_ini.RBF_KERNEL_PARAMETERS)
positions = array(ppositions + npositions, dtype=float64).T
position_features = rbf_svm.createFeatures(positions)
features.append_feature_obj(position_features)
motif_labels = append(ones(num_positives), -ones(num_negatives))
complete_labels = Labels(motif_labels)
rbf_kernel = GaussianKernel(position_features, position_features, \
kirmes_ini.RBF_KERNEL_PARAMETERS['width'])
kernel_array.append(rbf_kernel)
kernel.append_kernel(rbf_kernel)
#Kernel init
kernel.init(features, features)
kernel.set_cache_size(kirmes_ini.K_CACHE_SIZE)
svm = LibSVM(kirmes_ini.K_COMBINED_C, kernel, complete_labels)
svm.parallel.set_num_threads(kirmes_ini.K_NUM_THREADS)
#Training
svm.train()
if not os.path.exists(options.output_path):
os.mkdir(options.output_path)
html = {}
if options.contrib:
html["contrib"] = contrib(svm, kernel, motif_labels, kernel_array,
motifs)
if options.logos:
html["poims"] = poims(svm, kernel, kernel_array, motifs,
options.output_path)
if options.query:
html["query"] = evaluate(options, svm, kernel, features, motifs)
htmlize(html, options.output_html)
